Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) vs torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout)
As of Oct 15, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) leads torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) in 1 of 1 shared categories: Decision models.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Yes. SOTA in co-SOTA in Decision models.
torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout)
#35 Best current rank: #35 in Decision models, as of Oct 15, 2026.
| Category | Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) | torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) |
|---|---|---|
| Decision models | #1 · Co-SOTA · Decision models Margin 0 Jev Decision Index · Oct 14, 2026 | #35 · #35 in Decision models Margin 15.151515151515156 JevBench · Oct 8, 2026 |
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout): price per 1M tokens is unset in the catalog.
torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout): price per 1M tokens is unset in the catalog.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout): open weights.
torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout): open weights.
Decision models: As of Oct 15, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) leads torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) in Decision models at #1 against #35.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) · torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout)
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) or torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout)?
As of Oct 15, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) leads torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) in 1 of 1 shared categories: Decision models.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) or torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) for Decision models?
As of Oct 15, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) leads torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) in Decision models at #1 against #35.